Senior Engineer - AI / ML

Connecttel; Chennai District; On-site; INR 3,500,000 - 6,500,000; Full time

Job summary

Connecttel is seeking an AI/ML Senior Engineer in Chennai to lead hands-on development of core AI platforms. You will bridge architectural vision with code execution, building agentic workflows, knowledge graphs, and AI security safeguards.

You will work with an agile pod to deliver enterprise-grade AI systems, mentor teammates, and collaborate with product managers and client teams to resolve edge cases and accelerate feature delivery.

Qualifications

• 5+ years of software engineering experience, 3+ years delivering AI/ML or LLM-based products into production.
• Master’s degree or equivalent practical experience demonstrated through shipped products and professional certifications in AWS/GCP/Oracle/Claude.

Responsibilities

• Architect and code multi-modal LLM workflows and autonomous agentic systems.
• Build enterprise-grade AI platforms and guardrails for security and reliability.
• Collaborate with PMs, solution architects, and clients to accelerate feature delivery.
• Mentor team members and drive best-practice execution.

Skills

Python

TypeScript

Go

Java

MLOps

Education

Master’s in CS/DS/AI or equivalent practical experience

Tools

LangGraph

AutoGen

CrewAI

LangChain

LlamaIndex

PyTorch

HuggingFace

Qdrant

Pinecone

Milvus

Weaviate

Neo4j

RDF Ontologies

Job description

AI/ML Senior Engineer
Experience Level: 5+ Years
Location: Chennai
Full Time

Role Overview

We are seeking a high-ownership, hands-on AI / LLM Senior Engineer to drive the technical execution of our core AI platforms. In this role, you will bridge deep architectural vision with direct code-level execution.
You will collaborate with an agile engineering pod building enterprise-grade Agentic Workflows, Knowledge Graphs, and AI Security Safeguards. If you are driven by passion and innovation, determined to bend the limits to build something truly transformative this role is for you.

Key Responsibilities

Hands-On Agentic & Knowledge Systems Development:
Architect & Code: Build multi-modal LLM workflows and autonomous agentic systems using modern orchestration frameworks.
Knowledge Layer Integration: Implement knowledge graphs, dynamic ontologies, and advanced vector retrieval strategies (Hybrid Search, GraphRAG, Re-ranking) that go beyond standard naive RAG.

• AI Security & Guardrails:
  Deploy active safeguards against prompt injection, model jailbreaks, hallucination, and data leakage using core AI Security principles.
  Production MLOps, Eval & PerformanceLLM Ops: Build automated pipelines for continuous model evaluation (e.g., RAGAS, TruLens), dynamic prompt versioning, and latency tracking.
  Cost & Throughput Optimization: Optimize token consumption, context window management, caching, and model inference costs across multi-cloud deployments.
  Observability:
  Monitor model drift, data distribution shifts, and edge-case execution in live enterprise production environments.
  Cross-Functional Execution: Collaborate closely with Product Managers, Solution Architects, and client teams to resolve complex edge cases and accelerate feature delivery.
  Serve as a technical mentor, elevating team execution standards and unblocking complex algorithmic or system challenges daily.
  

Required Qualifications

Experience: 5+ years of core software engineering experience, including 3+ years specifically architecting and delivering AI/ML or LLM-based products into production.
Leadership: Proven track record leading agile pods, conducting technical design reviews, and mentoring developers.
Education: Master’s in computer science, Data Science, AI, or equivalent practical experience demonstrated through shipped products or open-source contributions and professional certifications in AWS/GCP/Oracle/Claude is mandatory.
Strong technical articulation and communication skills to engage with technical stakeholders, understand requirements, and present engineering solutions cleanly.

Technical Stack Requirements:

Languages & Core CS: Strong mastery of Python (FastAPI, PyDantic, Asyncio) with familiarity in TypeScript, Go, or Java.
Agentic Frameworks & AI Stack: Hands-on experience with modern LLM orchestration tools (LangGraph, AutoGen, CrewAI, LangChain, LlamaIndex), PyTorch, Hugging Face,and major LLM Provider APIs.
Vector Engines & Knowledge Graphs: Direct working experience with vector databases (Qdrant, Pinecone, Milvus, Weaviate) and Knowledge Graph technologies (Neo4j, RDF/Ontologies).
AI Security & Guardrails: Familiarity with adversarial prompt testing, red teaming concepts, and guardrail implementation.
MLOps & Infra: Practical experience with Docker, Kubernetes, GitHub Actions, MLflow, Weights & Biases, and serverless AI infrastructure on AWS/GCP/Azure.