About The Role Join our emerging technology team to build practical, high-value AI solutions for global clients. You will bridge cutting-edge generative AI research with production software engineering, crafting agentic workflows, semantic search systems, and automated evaluation suites.

Key Responsibilities
Architect and deploy autonomous AI agents with structured tool-calling and memory stores
Engineer hybrid enterprise RAG systems with semantic chunking, re-ranking, and vector embeddings
Implement robust evaluation datasets (evals) to measure hallucination rates and accuracy benchmarks
Optimize prompt chains, caching, and token usage to ensure predictable latency and unit economics
Implement security guardrails, PII redaction, and audit logging for enterprise compliance

Qualifications & Requirements
3+ years in software engineering with at least 1.5+ years focused on applied LLMs / GenAI
Robust proficiency in Python and TypeScript
Hands-on experience with frameworks like LangChain, LlamaIndex,



Instructor, or DSPy
Practical experience with vector databases (Qdrant, Pinecone, pgvector) and search techniques
Understanding of prompt engineering, few-shot techniques, and model evaluation methodologies
Disciplined engineering mindset regarding automated testing, observability, and cost control

Nice to Have
Experience fine-tuning open-source models (Llama 3, Mistral) with LoRA/QLoRA
Knowledge of local model execution with Ollama or vLLM
Experience deploying ML microservices with FastAPI, Docker, and Kubernetes

What We Offer Market-market-competitive salary and performance bonuses

Workstation hardware of your choice and cloud computing budget

Dedicated time and budget for AI experimentation and open-source contributions

Comprehensive health and wellness benefits

100% remote-first company culture

📌 Ai & Automation Engineer Kolkata Metropolitan Area (India)
🏢 OSSTAP
📍 India