AI/ML Engineer

We are seeking a highly skilled and self-driven Machine Learning Engineer with 3–4

years of hands-on experience in Generative AI, LLM-based systems, prompt

engineering, vector databases, and agentic AI automation. The ideal candidate will

have a strong background in Python, knowledge retrieval systems, and deploying AI-

powered automation for tasks involving documents, communication, and workflows.

You will work at the forefront of AI-driven automation, helping us build intelligent

systems that interact with unstructured data, automate decision-making, and deliver

real-time insights using cutting-edge Gen AI tools and frameworks.

Key Responsibilities:

• Design, build, and deploy AI agents and agentic workflows for document

understanding, communication automation, and knowledge retrieval.

• Develop, fine-tune, and optimize LLM prompts, RAG pipelines, and memory-

based systems for contextual AI.

• Integrate and manage vector databases (e.g., Pinecone, Weaviate, FAISS) for

scalable semantic search and retrieval.

• Develop and maintain Python-based pipelines, APIs, and microservices for AI

automation tasks.

• Work with structured and unstructured data, including PDFs, emails, and text

data, to generate actionable insights using Gen AI.

• Collaborate with product, data, and engineering teams to design scalable AI

solutions.

• Evaluate and integrate external LLM APIs (e.g., OpenAI, Anthropic, Mistral, etc.)

and open-source LLMs (e.g., Llama, Mistral, etc.).

• Monitor and optimize AI model performance, latency, and cost. Stay updated on advancements in agentic AI, LLM frameworks, vector

search, and Gen AI tools; recommend adoption where appropriate.

Required Skills & Qualifications:

• 3–4 years of experience in Machine Learning / AI engineering, with a focus on

Gen AI and LLMs.

• Proficiency in Python, including frameworks like LangChain, LlamaIndex,

FastAPI, Pydantic, etc.

• Strong experience in prompt engineering and LLM integration (e.g., OpenAI,

Claude, Mistral).

• Hands-on experience with vector databases (e.g., Pinecone, Weaviate, FAISS,

Chroma).

• Experience building retrieval-augmented generation (RAG) systems.
• Familiarity with agentic AI frameworks (e.g., LangGraph, AutoGen, CrewAI,

AutogenStudio).

• Strong understanding of document processing, including OCR, PDF parsing,

text embeddings, and summarization.

• Comfortable working with APIs, webhooks, and automation of communication

workflows (e.g., email, chat, scheduling).

• Solid understanding of data structures, algorithms, and performance

optimization.

• Excellent problem-solving skills, ownership mindset, and ability to work in a fast-

paced environment.

Nice to Have:

• Experience with LLM fine-tuning or model distillation.
• Knowledge of Docker, Kubernetes, and cloud services (e.g., AWS, GCP, Azure).
• Familiarity with open-source LLMs (e.g., Llama, Mistral, Zephyr) and

deployment using vLLM, Ollama, or Modal.

• Exposure to PostgreSQL, Redis, and task queues like Celery or RQ.
• Experience with AI observability tools (e.g., LangSmith, Helicone, Phoenix) is a

plus.Soft Skills:

• Strong written and verbal communication skills.
• Ability to manage ambiguity and drive projects independently.
• Passion for staying updated with AI research and applying it to real-world use

cases.

Job Type: Full-time

Pay: Up to ₹1,900,000.00 per month

Benefits:

• Health insurance

Work Location: In person