AI Systems Architecture LeadRecro • Haryāna, Republic Of India, IN
AI Systems Architecture Lead
Recro • Haryāna, Republic Of India, IN
4 days ago
Job descriptionSize and optimize infrastructure for cost and performance : model throughput / latency, concurrency, autoscaling policies, CPU / GPU needs, memory footprints, vector index sizing, storage / egress, and token budgets. Lead deep-dive debugging and incident resolution : profile bottlenecks, fix defects, stabilize services; Establish reference implementations for multi-agent frameworks (Semantic Kernel preferred; Architect retrieval and hybrid search systems : ingestion, chunking, embeddings, ranking, caching, freshness, and grounding; Productionize on AWS using Amazon EKS, S3, SQS / SNS, and AWS Bedrock; integrate identity (Okta / IAM), secrets (AWS Secrets Manager), eventing, and observability; Make systems observable : distributed tracing, metrics, and logs using OpenTelemetry and Datadog; Build evaluation and promotion workflows : prompt / flow tests, golden sets, offline batch runs, A / B experiments, regression suites, and rollout gates. Design security and safety controls : threat modeling, prompt-injection defense, sandboxed tools, policy enforcement, red-team testing, PII / data governance, and audit trails. Define platform standards : reusable SDKs, connectors, CI / CD templates, runbooks, and architecture review checklists. Partner with product, data, and SRE teams to plan capacity, disaster recovery, multi-region posture, and upgrade paths; Mentor engineers and review PRs with a focus on reliability, correctness, and maintainability. 7–10 years in software / AI engineering with at least 4+ years building GenAI applications and 2+ years architecting production agentic systems. Strong hands-on expertise in Python 3.11+ (typing, asyncio, packaging, profiling, pytest); Experience with one or more agent frameworks (Semantic Kernel, LangGraph, AutoGen, CrewAI) and function / tool calling with schema and argument validation. Proven design of GenAI / RAG / hybrid retrieval systems using AWS Bedrock, OpenSearch Serverless, or other vector databases; Deep knowledge of AWS architecture : Amazon EKS, Bedrock, S3, SQS / SNS, RDS (SQL Server / PostgreSQL), ElastiCache (Redis), Secrets Manager, IAM / Okta, Kong API Gateway, OpenSearch Serverless, and Datadog. Observability expertise : distributed tracing (OpenTelemetry), metrics, logs, correlation IDs, and service-level objectives; Cost and performance engineering mindset : capacity modeling, GPU / CPU sizing, autoscaling (HPA), batching / streaming, caching, and FinOps discipline. Security and safety fundamentals : least privilege, data isolation, policy enforcement, content moderation, jailbreak / PII defenses, and compliance awareness. Excellent technical communication : clear diagrams, ADRs, design docs; Multi-agent orchestration patterns : task decomposition, coordinator-worker, human-in-the-loop, graph-based planning. Deep expertise with vector databases and retrieval : OpenSearch Serverless, Pinecone, pgvector, Redis. Evaluation frameworks : red teaming, automated guardrails, regression testing, rollout gates, canary deployments. Frontend integration for agent UIs (streaming responses, tool traces), secure connector APIs, and AuthN / Z best practices. Policy-as-code (OPA) and multi-tenant architecture (RBAC, quotas, usage metering). Knowledge of Kong API Gateway, LaunchDarkly / Flipt for feature management, and NeMo Guardrails for runtime safety. CI / CD exposure (build / test with GitHub Actions, deployments via Terraform / AWS IaC templates). Core Tech Stack (our core; Python 3.11+, FastAPI, Pydantic v2, SQLAlchemy 2.X, Alembic, pytest. Amazon EKS, AWS Bedrock, Amazon SQS / SNS, Amazon RDS (SQL Server / PostgreSQL), ElastiCache (Redis). Amazon S3 for storage, Amazon ECR for container images, OpenSearch Serverless for vector storage. AWS Secrets Manager, Okta IAM, NeMo Guardrails, Kong API Gateway. OpenTelemetry + Datadog for observability and monitoring. Custom RAG Services, Bedrock Knowledge Base, and LLM evaluation with Phoenix, Arize, and Promptfoo.
Overview
Own the end-to-end architecture of production AI systems with a strong hands-on bias. You’ll design robust, cost-efficient, and secure agentic / GenAI solutions on AWS. Part of your job will be to unblock lead developers by debugging code, optimizing performance, and guiding best practices. Expect to turn complex requirements into scalable, observable, and well-governed platforms.
Responsibilities
- Define target architectures for agentic systems (planning / reasoning / tool-calling), GenAI / RAG pipelines, and evaluation loops;
produce clear design documents with Flow / UML / sequence diagrams and AWS deployment topologies.
pair-program with developers to raise the engineering bar.
LangGraph / AutoGen / CrewAI acceptable), tool / function schemas, validation, memory, grounding, and multi-step planning.
evaluate recall, precision, and hallucination risk.
enforce SLIs / SLOs and error budgets.
standardize dashboards,alerts, and tool / trace replay.
lead readiness reviews and post-incident RCAs.
Must Have
able to dive into code,fix bugs, and optimize performance-critical paths.
grounding and retrievalevaluation experience.
mature incident response and on-call practices.
empathetic, structured code and architecture reviews.
Good to Have
equivalents welcome)
Create a job alert for this search
Ai Lead • Haryāna, Republic Of India, IN
Related jobs
)
AI Systems Architect
Recro • Haryāna, Republic Of India, IN
This is a highly hands-on role requiring deep architectural insight, coding proficiency, and an obsession with performance, scalability, and reliability.
You’ll architect secure, cost-efficient AI p...Show more
Last updated: 4 days ago • Promoted
AI Solutions Architect
PBPartners • Haryāna, Republic Of India, IN
AI Tech Lead who is first a builder, and second a product translator.AI-powered solutions that directly impact PB Partners’ agent network, customer journeys, and internal operations.Build AI applic...Show more
Last updated: 4 days ago • Promoted
AI Infrastructure & Automation Architect
Recro • Haryāna, Republic Of India, IN
Own the end-to-end architecture of production AI systems with a strong hands-on bias.You’ll design robust, cost-efficient, and secure agentic / GenAI solutions on AWS.
Part of your job will be to unbl...Show more
Last updated: 4 days ago • Promoted
AI Solutions Architect
Crane Authentication (NXT) • Haryāna, Republic Of India, IN
Location - Gurugram / Bangalore.As a partner to businesses and governments,.Customers from different business sectors and levels of government trust our team of 1,250 people for their expertise in ...Show more
Last updated: 4 days ago • Promoted
Ai Solutioning and Innovation Lead
Sirius AI • Haryāna, Republic Of India, IN
We are seeking a dynamic and visionary Associate Director to lead solutioning and innovation initiatives within our AI Innovations Lab.
This role involves designing, delivering, and scaling AI / ML so...Show more
Last updated: 2 days ago • Promoted
Lead AI / Backend Systems Architect
T3RA Logistics • Haryāna, Republic Of India, IN
Founding AI and Backend Engineer.Be the Technical Backbone of FreightX’s Revolution (A stealth mode - T3RA Logistics Spinoff company).
As our Founding AI and Backend Engineer, you’ll architect scala...Show more
Last updated: 4 days ago • Promoted
Generative AI Platform Lead
Recro • Haryāna, Republic Of India, IN
This is a highly hands-on role requiring deep architectural insight, coding proficiency, and an obsession with performance, scalability, and reliability.
You’ll architect secure, cost-efficient AI p...Show more
Last updated: 4 days ago • Promoted
AI Solutions Lead
Advanced AI research and product company • Haryāna, Republic Of India, IN
Our client is an advanced AI research and product company focused on building intelligent systems that combine deep reasoning, natural language understanding, and adaptive learning.Its mission is t...Show more
Last updated: 4 days ago • Promoted
Generative AI Solutions Architect
Birdeye • Haryāna, Republic Of India, IN
Lead Data Scientist -Agentic AI.Birdeye is the highest-rated reputation, social media, and customer experience platform for local businesses and brands.
Over 150,000 businesses use Birdeye’s AI-powe...Show more
Last updated: 4 days ago • Promoted
Data Architect – Ai Platform
Birdeye • Haryāna, Republic Of India, IN
Job Title : Data Architect – AI Platform.Department : Engineering / Data Platform.This role is central to building the.You’ll architect and implement the systems that transform raw data into.You won’...Show more
Last updated: 4 days ago • Promoted
Ai Tech Architect
Recro • Haryāna, Republic Of India, IN
Own the end-to-end architecture of production AI systems with a strong hands-on bias.You’ll design robust, cost-efficient, and secure agentic / GenAI solutions on AWS.
Part of your job will be to unbl...Show more
Last updated: 4 days ago • Promoted
AI Data Architect
Birdeye • Haryāna, Republic Of India, IN
Job Title : Data Architect – AI Platform.Department : Engineering / Data Platform.This role is central to building the.You’ll architect and implement the systems that transform raw data into.You won’...Show more
Last updated: 4 days ago • Promoted
Solutions Architect Lead
Nokia • Haryāna, Republic Of India, IN
Join us in creating the technology that helps the world act together.We are a B2B technology innovation leader, pioneering networks that sense, think and act™, putting the world’s people, machines ...Show more
Last updated: 4 days ago • Promoted
AI Insights Architect
Birdeye • Haryāna, Republic Of India, IN
Job Title : Data Architect – AI Platform.Department : Engineering / Data Platform.This role is central to building the.You’ll architect and implement the systems that transform raw data into.You won’...Show more
Last updated: 4 days ago • Promoted
Generative AI Solutions Lead
PepsiCo • Haryāna, Republic Of India, IN
The Senior Technical Architect – Generative AI and Agent Factory is responsible for leading the end-to-end architecture, design, and strategic enablement of PepsiCo's enterprise-grade GenAI platfor...Show more
Last updated: 4 days ago • Promoted
AI Systems Developer
Crane Authentication (NXT) • Haryāna, Republic Of India, IN
Location - Gurugram / Bangalore.As a partner to businesses and governments,.Customers from different business sectors and levels of government trust our team of 1,250 people for their expertise in ...Show more
Last updated: 4 days ago • Promoted
AI / ML Solutions Architect
Incedo Inc. • Haryāna, Republic Of India, IN
Technical Lead – Data Science & Generative AI (Python / LLMs).Incedo, you will drive the design, development, and deployment of advanced machine learning, deep learning, and generative AI solutions.Y...Show more
Last updated: 2 days ago • Promoted
AI Solutions Architect
PepsiCo • Haryāna, Republic Of India, IN
PepsiCo Data Analytics & AI Overview : .With data deeply embedded in our DNA, PepsiCo Data, Analytics and AI (DA&AI) transforms data into consumer delight.
We build and organize business-ready data th...Show more
Last updated: 4 days ago • Promoted