Sr AI / ML Engineer

What You’ll Do

• Design, architect, and implement state-of-the-art Generative AI applications and agentic systems using modern AI frameworks such as LangChain, LlamaIndex, or custom orchestration layers.
• Seamlessly integrate large language models (e.g., GPT-4, Claude, Mistral) into production workflows, tools, or customer-facing applications.
• Build scalable, reliable, and high-performance backend systems using Python and modern frameworks to power GenAI-driven features.
• Take ownership of prompt engineering, tool usage, and long / short-term
• memory management to develop intelligent and context-aware agents.
• Deliver high-quality results rapidly by leveraging Cursor and other AI-assisted "vibe coding" environments for fast development, iteration, and debugging.
• Use vibe coding tools effectively to accelerate delivery, reduce development friction, and fix bugs quickly with minimal overhead.
• Participate in and lead the entire SDLC, from requirements analysis and architectural design to development, testing, deployment, and maintenance.
• Write clean, modular, well-tested, and maintainable code, following best practices including SOLID principles and proper documentation standards.
• Proactively identify and resolve system-level issues, performance bottlenecks, and edge cases through deep debugging and optimization.
• Collaborate closely with cross-functional teams—including product, design, QA, and ML—to iterate quickly and deliver production-ready features.
• Execute end-to-end implementations and POCs of agentic AI frameworks to validate new ideas, de-risk features, and guide strategic product development.
• Contribute to internal tools, libraries, or workflows that enhance development speed, reliability, and team productivity.

What You Bring

Extensive Python Expertise :

Hands-on experience in Python development, with a focus on clean, maintainable, and scalable code.

Mastery of OOP, SOLID principles, and design patterns; proven experience designing and

leading complex software architectures.

Practical experience with frameworks like LangChain, LlamaIndex, or other agent

orchestration libraries.

Direct experience integrating APIs from OpenAI, Anthropic, Cohere, or similar providers.

Strong understanding of prompt design, refinement, and optimization for LLM-based

applications.

Experience architecting and implementing Retrieval Augmented Generation (RAG) pipelines

and solutions.

Exposure to FAISS, Pinecone, Weaviate, or similar tools for semantic retrieval.

Solid foundation in Natural Language Processing and core machine learning concepts

Familiarity with cloud platforms like AWS, GCP, or Azure, including deployment of GenAI

solutions at scale.

Proficient with Docker, with working knowledge of Kubernetes.

Experience with platforms such as MLflow, Weights & Biases, or equivalent tools.

Exposure to knowledge graphs, ontologies, and semantic search technologies.