Senior AI Engineer_ (Backend)

Tredence; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Tredence is seeking a Senior/Lead AI Engineer (Backend) to architect and scale enterprise-grade AI Agent platforms. The role demands deep expertise in Agentic AI, RAG architectures, distributed AI systems, and production deployment, with strong technical leadership across teams.

The candidate should have 8-12 years of experience, fluency with Python/TypeScript, and a track record of building scalable backend services for AI products.

Qualifications

• 8-12 years of experience in AI engineering and backend architecture.
• Proven track record designing production-grade multi-agent systems.
• Experience with agentic AI, RAG architectures, and distributed AI systems.

Responsibilities

• Define AI architecture and engineering best practices.
• Drive AI platform strategy and roadmap.
• Mentor engineers and establish development standards.

Skills

Agent memory

Planning & Reasoning

Human-in-the-Loop Workflows

Stateful Agents

MCP Architecture

3+ years experience in multi-agent

Tools

LangGraph

LlamaIndex Workflows

CrewAI

AutoGen

Agent Mesh Architectures

Pinecone

Qdrant

Weaviate

pgVector

OpenAI

Anthropic

Gemini

Llama

Mistral

DeepSeek

Job description

Senior AI Engineer (Backend)

Experience: 8-12 Years

Role Summary

We are seeking a Senior/Lead AI Engineer to architect and scale enterprise-grade AI Agent platforms. The ideal candidate should possess deep expertise in Agentic AI, RAG architectures, distributed AI systems, and production deployment, while providing technical leadership across teams.

Primary Skills (Must Have) Agentic AI Architecture

• 3+ years of extensive experience designing production-grade multi-agent systems.
• Expertise in:
  • LangGraph
  • LlamaIndex Workflows
  • CrewAI
  • AutoGen
  • Agent Mesh Architectures
• Strong understanding of:
  • Stateful Agents
  • Agent Memory
  • Planning & Reasoning
  • Human-in-the-Loop Workflows
  • MCP Architecture

Advanced RAG Systems

• Expertise in:
  • Hybrid Search
  • Semantic Search
  • Reranking
  • GraphRAG
  • Knowledge Graph Integration
  • Agentic RAG
• Proficiency with:
  • Pinecone
  • Qdrant
  • Weaviate
  • pgVector

AI Platform Engineering

• Design scalable AI platforms and shared AI services.
• Build reusable APIs, SDKs, AI frameworks, and accelerator components.
• Experience supporting enterprise-scale workloads.

Full Stack Engineering

• Strong Python expertise.
• Experience with TypeScript/Node.js.
• Experience designing highly scalable backend services.
• Familiarity with frontend frameworks for AI product development.

LLM Ecosystem

• Extensive experience using:
  • OpenAI
  • Anthropic
  • Gemini
  • Open Source Models (Llama, Mistral, DeepSeek, etc.)
• Fine-tuning and model optimization exposure.
• Prompt engineering and reasoning optimization.

Evaluation, Monitoring & Reliability

• Design enterprise-level AI quality frameworks.
• Build:
  • Evaluation Pipelines
  • Benchmarking Frameworks
  • Guardrails
  • Safety Checks
• Expertise with:
  • LangSmith
  • LangFuse
  • Arize Phoenix
  • OpenTelemetry

Cloud & Infrastructure

• Expert-level experience with:
  • AWS/Azure/GCP
  • Kubernetes
  • Docker
  • CI/CD
  • Infrastructure as Code
• Experience leveraging GPU infrastructure and inference optimization.

Secondary Skills (Good to Have) Big Data & Streaming

• Apache Spark
• Hadoop
• Kafka
• Flink
• Beam

Advanced AI Capabilities

• Multimodal AI
• Voice AI Agents
• Computer Vision Integration
• Real-time AI applications

Graph Technologies

• Neo4j
• Knowledge Graphs
• GraphRAG Architectures

Enterprise Architecture

• Spring Boot
• Large-scale Microservices
• Event-driven Systems

Optimization

• CUDA
• Quantization
• Model Serving
• VLLM/TGI
• GPU Performance Tuning

Key Responsibilities Technical Leadership

• Define AI architecture and engineering best practices.
• Drive AI platform strategy and roadmap.
• Mentor engineers and establish development standards.

Solution Ownership

• Lead AI product delivery from concept to production.
• Establish reliability, scalability, and governance standards.
• Drive AI adoption across business functions.

Innovation

• Evaluate emerging AI technologies.
• Introduce new Agentic AI, RAG, and reasoning capabilities.
• Balance innovation, cost, performance, and business value.