Generative AI Engineer
Talentmatics
- Location
- Mumbai, Maharashtra, India
- Job type
- Full-time
Required skills
- LangChain
- Python
- AWS
- Azure
- compliance
- DevOps
- Docker
- FastAPI
- Flask
- GCP
- microservices
- NLP
- Pytorch
- Vertex
About the role
Talentmatics
Website:
talent-matics.com
Job details:
Generative AI Engineer
Location: Mumbai
Notice Period : Immediate to 30 Days
Experience: 3-6 years
Key Responsibilities
- Design and develop LLM-powered applications using models such as OpenAI, Claude, Mistral, and other foundation models.
- Build RAG pipelines using vector databases such as Pinecone, FAISS, pgvector, ChromaDB, Qdrant, Milvus, or Weaviate.
- Develop AI applications using LangChain, LlamaIndex, and related GenAI frameworks.
- Build AI agents and multimodal AI solutions involving text, audio, and images.
- Design and optimize prompt templates, chains, agents, and AI workflows.
- Benchmark commercial and open-source LLMs based on accuracy, performance, and cost.
- Evaluate and implement fine-tuning approaches such as PEFT and LoRA where applicable.
- Deploy GenAI solutions on AWS, GCP, or Azure using services such as Bedrock, SageMaker, or Vertex AI.
- Develop scalable APIs and microservices using FastAPI/Flask.
- Implement MLOps practices including CI/CD, model monitoring, drift detection, canary releases, and retraining.
- Ensure performance, security, observability, responsible AI, and compliance of GenAI applications.
- Collaborate with Solution Architects, DevOps teams, Data Scientists, and customers to deliver PoCs and enterprise-grade solutions.
- Document technical frameworks, best practices, risks, and learnings.
Required Skills
- 3+ years of experience in NLP/ML/AI, with at least 3 years of hands-on GenAI experience.
- Strong programming skills in Python.
- Hands-on experience with Generative AI, LLMs, RAG, embeddings, and prompt engineering.
- Experience with LangChain and/or LlamaIndex.
- Strong knowledge of PyTorch and Hugging Face.
- Experience working with LLM APIs such as OpenAI, Anthropic, or Hugging Face.
- Hands-on experience with vector databases such as Pinecone, FAISS, pgvector, Qdrant, Milvus, or Weaviate.
- Experience with at least one cloud platform: AWS, GCP, or Azure.
- Knowledge of transformer architectures and embedding techniques.
- Experience developing APIs using FastAPI or Flask.
- Good understanding of MLOps, CI/CD, Docker, security, and model monitoring.
- Strong communication and stakeholder management skills.
Click on Apply to know more.
This page is fully interactive when JavaScript is enabled. Please enable JavaScript to apply or browse related roles.