About the Role - We are looking for a Senior Software Engineer – AI who is passionate about building intelligent systems that solve real-world problems. You’ll work at the intersection of machine learning, large language models (LLMs), and backend engineering, turning research into production-ready systems. This is a hands-on engineering role with a strong emphasis on scalable AI integration, prompt engineering, RAG (retrieval-augmented generation), and building intelligent APIs and microservices.
What You'll Do -
- Design and build AI-powered applications using LLMs (OpenAI, LLaMA, Mistral, etc.), vector databases, and embedding models
- Build scalable backend systems and APIs (Python, FastAPI, Node.js, etc.) to serve AI features in production
- Develop retrieval-augmented generation (RAG) pipelines and manage unstructured knowledge bases (PDFs, docs, audio)
- Optimize inference pipelines for low latency and cost (e.g., with Ollama, vLLM, or LangChain)
- Work with tools like Whisper, HuggingFace, and Pinecone / ChromaDB / Weaviate
- Write clean, modular code and lead by example in engineering excellence
- Collaborate closely with product, design, and ML teams to rapidly prototype and ship features
Must-Have Skills -
4+ years of software engineering experience (Python preferred)Hands-on experience with LLMs, generative AI, or custom ML workflowsStrong understanding of NLP, embeddings, and vector searchExperience with FastAPI / Flask / Django and REST APIsSolid grounding in Docker, Git, and CI / CD pipelinesComfortable with cloud platforms (AWS / GCP / Azure) and containerized deploymentsStrong debugging, performance tuning, and system design skillsGood to Have -
Experience with LangChain, Haystack, or custom RAG frameworksFamiliarity with Whisper (speech-to-text) or audio / video transcription pipelinesFrontend knowledge in React.js is a bonusExperience scaling AI systems to serve 10k+ usersMLOps exposure (MLFlow, Weights & Biases, etc.)What We Look For -
You thrive in ambiguity and move fast from prototype to productionYou think deeply about user experience in AI-driven applicationsYou enjoy collaborating across teams and sharing your learningsYou keep up with emerging research but know how to make it real