Senior AI Engineer

Tekreant; Hyderabad; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Tekreant in Hyderabad is seeking a Senior AI Engineer to design, develop, and deploy production-grade AI systems and intelligent automation platforms. The role emphasizes building real-world AI applications, including conversational AI, RAG pipelines, voice AI, and enterprise automation.

You will work with multiple LLMs (OpenAI, Anthropic, Gemini and open-source options), design scalable back-end APIs with FastAPI or Node.js, and collaborate with cross-functional teams.

Qualifications

• Strong understanding of LLMs, embeddings, transformers, and inference workflows.
• Experience with RAG architectures and vector search.
• Experience with prompt engineering and tool calling.
• Familiarity with fine-tuning concepts (LoRA/QLoRA preferred).

Responsibilities

• Design and develop AI-powered applications using modern LLM frameworks.
• Build multi-agent workflows using LangGraph, LangChain, or similar frameworks.
• Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases.
• Integrate OpenAI, Anthropic, Gemini, and open-source LLMs.
• Develop scalable backend APIs using FastAPI or Node.js.
• Work with PostgreSQL, MongoDB, Redis, and vector databases.
• Deploy and manage AI services using Docker and cloud platforms (AWS/Azure/GCP).
• Optimize AI workflows for latency, scalability, reliability, and cost.
• Build real-time AI systems including voice AI and streaming pipelines.
• Collaborate with cross-functional teams to translate business requirements into AI solutions.
• Mentor junior engineers and participate in architecture discussions.

Skills

LLMs

Agentic AI

Python

FastAPI

LangChain

LangGraph

Prompt engineering

REST APIs

Distributed systems

Tools

Docker

AWS

Azure

GCP

PostgreSQL

MongoDB

Redis

FastAPI

Hugging Face

Job description

Senior AI Engineer - Job Description

Location: Hyderabad
Experience: 5+ Years
Employment Type: Full-Time

Job Description

We are seeking a highly skilled Senior AI Engineer to design, develop, and deploy production-grade AI systems and intelligent automation platforms. The ideal candidate should have strong expertise in Large Language Models (LLMs), Agentic AI systems, backend engineering, and scalable AI infrastructure.
The role involves building real-world AI applications including conversational AI, RAG pipelines, voice AI systems, multi-agent workflows, healthcare AI solutions, and enterprise automation platforms.

Key Responsibilities

• Design and develop AI-powered applications using modern LLM frameworks
• Build multi-agent workflows using LangGraph, LangChain, or similar frameworks
• Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases
• Integrate OpenAI, Anthropic, Gemini, and open-source LLMs
• Develop scalable backend APIs using FastAPI or Node.js
• Work with PostgreSQL, MongoDB, Redis, and vector databases
• Deploy and manage AI services using Docker and cloud platforms (AWS/Azure/GCP)
• Optimize AI workflows for latency, scalability, reliability, and cost
• Build real-time AI systems including voice AI and streaming pipelines
• Collaborate with cross-functional teams to translate business requirements into AI solutions
• Mentor junior engineers and participate in architecture discussions

Required Skills

AI & Machine Learning

• Strong understanding of LLMs, embeddings, transformers, and inference workflows
• Experience with RAG architectures and vector search
• Experience with prompt engineering and tool calling
• Familiarity with fine-tuning concepts (LoRA/QLoRA preferred)

Programming & Frameworks

• Strong Python programming skills
• Experience with FastAPI
• Experience with LangChain / LangGraph
• Familiarity with Hugging Face ecosystem
• Experience with REST APIs and asynchronous programming

Databases & Infrastructure

• PostgreSQL
• MongoDB
• Redis
• Docker
• Linux
• Cloud platforms (AWS/Azure/GCP)

Preferred / Good-to-Have Skills

• Voice AI systems (Whisper, Deepgram, ElevenLabs, etc.)
• Healthcare AI / Clinical NLP
• HL7/FHIR integrations
• OCR / Document AI pipelines
• React / TypeScript

Candidate Profile

• Strong problem-solving and system design skills
• Ability to independently build and deploy production-ready solutions
• Startup mindset with ownership and execution focus
• Good communication and collaboration skills
• Experience working on end-to-end AI products is preferred