LLM Engineer / Agentic AI talent

Senior AI Engineer tion

Company: SandLogic

Location: Bangalore / Hybrid

Experience: 48 years

Employment Type: Full-time

About the Role

We are looking for an LLM Engineer to accelerate our Generative AI roadmap by building scalable, production-grade systems powered by Large Language Models (LLMs). This role goes beyond prompt design you will own the end-to-end lifecycle of LLM-powered products, from prototyping and agent orchestration to deployment, evaluation, safety, and optimization.

You will work on AI agents, enterprise workflow automation, Retrieval-Augmented Generation (RAG), multi-model orchestration, and voice-integrated AI systems, enabling real-world autonomous workflows for enterprise customers. This is a highly cross-functional role working across product, platform, research, and customer engineering teams.

Key Responsibilities

• Design and build LLM-powered applications, copilots, and AI agents for enterprise workflows
• Develop RAG pipelines, semantic search systems, and context-aware reasoning workflows
• Build internal tools, APIs, SDKs, and developer utilities for scalable LLM integrations
• Implement tool calling / function calling, MCP integrations, and external API orchestration
• Design multi-agent workflows, task decomposition, memory, and long-horizon execution pipelines
• Optimize inference systems for latency, cost, throughput, and reliability
• Implement caching, batching, fallback routing, prompt versioning, and model experimentation systems
• Build evaluation frameworks covering quality, hallucination checks, latency, and safety metrics
• Deploy production systems on AWS/GCP with Docker and Kubernetes
• Define observability, tracing, logging, and guardrails for responsible LLM deployments
• Collaborate with product, research, and platform teams to convert AI use cases into production systems
• Stay updated with latest developments in LLMs, AI agents, voice AI, multimodal systems, and inference optimization

Core Requirements

• Strong programming expertise in Python and backend system design
• Hands-on experience with LangChain, LangGraph, Haystack, PydanticAI, AutoGen, or similar frameworks
• Strong understanding of LLM architectures, tokenization, embeddings, inference workflows, and context engineering
• Experience integrating OpenAI, Anthropic, Azure OpenAI, or open-source models into production systems
• Strong knowledge of RAG pipelines, vector databases, reranking, chunking, and semantic retrieval
• Experience in AI agents, autonomous workflows, and memory systems
• Familiarity with MCP, tool-use frameworks, workflow orchestration, and event-driven architectures
• Experience with cloud-native deployment, containers, CI/CD, and observability tools
• Strong problem-solving and stakeholder communication skills

Preferred / Good-to-Have Skills

• Experience with voice AI pipelines (ASR, TTS, voice-to-LLM)
• Exposure to multimodal AI systems (vision + language + voice)
• Experience with quantization, distillation, model compression, and inference optimization
• Familiarity with enterprise compliance, security, and governance systems
• Experience building customer-facing GenAI products
• Knowledge of evaluation harnesses, benchmark datasets, and safety frameworks

What Youll Build

• Autonomous AI agents for enterprise operations
• Multi-step reasoning workflows with external tools and APIs
• Knowledge copilots and enterprise search assistants
• Voice-enabled real-time assistants
• Scalable GenAI platforms with governance and observability

Why Join SandLogic

• Work on cutting-edge Agentic AI and enterprise LLM systems
• Build production AI systems used in real-world workflows
• Opportunity to shape next-generation AI workforce platforms
• High ownership, fast-moving engineering culture
• Strong scope across LLMs, voice AI, multimodal AI, and edge deployments

How to Apply

Send your profile to people@sandlogic.com or DM directly on LinkedIn.