About The Opportunity
A fast-scaling AI-first technology consultancy operating across enterprise sectors including BFSI, healthcare, and logistics, we enable clients to deploy GenAI-powered automation, intelligent document processing, and conversational AI at scale. We partner with global tech stacks and build custom GenAI solutions that drive measurable ROI—focusing on LLM fine-tuning, RAG architectures, and agent-based workflows for real-world business impact.
Role & Responsibilities
- Design and deploy production-grade GenAI pipelines using LLMs (GPT, Llama, Mistral) for use cases including summarization, Q&A, and agent orchestration.
- Implement RAG (Retrieval-Augmented Generation) systems with ChromaDB, Pinecone, or FAISS for context-aware LLM responses.
- Develop LangChain/LangGraph-based agents with tool-calling, memory, and multi-step reasoning for enterprise automation.
- Optimize model inference latency and cost via quantization, prompt engineering, and cache-layer strategies on cloud platforms.
- Collaborate with data engineers to build ingestion & vectorization pipelines from structured/unstructured sources.
- Document architecture decisions, maintain model versioning, and implement observability (tracing, logging, drift detection).
Skills & Qualifications
Must-Have
- LangChain
- OpenAI API
- LLM fine-tuning
- Vector databases
- Prompt engineering
- Python
- REST API development
- Cloud deployment (AWS/Azure/GCP)
Preferred
- LangGraph
- LlamaIndex
- MLflow or Weights & Biases
Benefits & Culture Highlights
- Work with Fortune 500 clients on mission-critical GenAI deployments from day one.
- Weekly upskilling sessions + access to cutting-edge research papers and internal hackathons.
- On-site collaborative environment in Tier-1 Indian cities with flexible core hours.
Skills: ai,genai,aws,llm
