MSD logo

Senior Specialist, AI Engineering

MSD
NewPosted today

LOCATION

Hyderabad · Hybrid

EXPERIENCE

7 - 11 Years

TYPE

FullTime

SKILLS REQUIRED

PythonRAGPrompt EngineeringLarge Language ModelsAI AgentsObservabilitymodel context protocol

Job description

Overview

Senior AI Engineer role in the Hyderabad Tech Center driving end-to-end development of GenAI applications, including prompt engineering, fine-tuning, RAG pipelines, and LLM-based workflows, with technical leadership and mentoring responsibilities.

What you'll do

  • Design and implement Agentic AI systems leveraging frameworks such as LangChain, Google ADK, Strands, and Semantic Kernel, enabling multi-step reasoning and task orchestration.
  • Develop and operationalize multi-agent systems, incorporating patterns such as planning, tool usage, memory, and iterative reasoning.
  • Apply advanced prompt engineering techniques (React, few-shot learning, chain-of-thought, prompt chaining) to improve accuracy, determinism, and robustness of LLM systems.
  • Establish AgentOps practices, including observability, tracing, logging, and performance monitoring for production-grade AI systems.
  • Build multimodal AI solutions, integrating text with images or structured data to support complex enterprise use cases.
  • Apply harness engineering practices to systematically design, test, and evaluate AI/agent workflows across different scenarios.
  • Develop reusable agent tooling and integrations, enabling interaction with enterprise services, tools, and workflows, including Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication patterns.
  • Collaborate with cross-functional stakeholders to translate business problems into scalable GenAI-driven solutions.
  • Leverage modern AI developer tooling such as Claude CLI, GitHub Copilot, Vertex AI, and Codex to accelerate development workflows.
  • Support deployment and operationalization of AI solutions using cloud platforms such as AWS and GCP.

What you'll need

  • Educational requirement is mandatory: Masters in a relevant quantitative, applied field (Statistics, Econometrics, Computer Science, Mathematics, Engineering).
  • 7-11 years of experience in Software Engineering.
  • Minimum of 3 years of work experience in the end-to-end lifecycle of ML model development and deployment into production within a cloud infrastructure.
  • Deep expertise in RAG architectures, including embedding generation, retrieval optimization, grounding, and context management.
  • Proficiency in prompt engineering techniques (ReAct, chain-of-thought, few-shot learning, prompt chaining, instruction refinement).
  • Hands-on experience building and deploying LLM-powered applications and agent-based systems in production environments.
  • Experience implementing AgentOps practices, including observability, tracing, logging, and performance evaluation of AI systems.
  • Strong Python programming skills with experience in tooling, function-calling, and agent-driven integrations.
  • Experience designing context engineering strategies, including chunking, context optimization, and prompt-context alignment.
  • Familiarity with harness engineering approaches for systematic testing, validation, and benchmarking of AI systems.
  • Understanding of Model Context Protocol (MCP) and Agent-to-Agent (A2A) interaction patterns.
  • Experience building ML/AI pipelines, including automation, orchestration, and CI/CD integration.
  • Solid expertise in NLP and text processing, including tokenization, embeddings, and preprocessing pipelines.
  • Understanding of transformer architectures and modern LLM ecosystems.
  • Understanding of basic machine learning, including supervised/unsupervised learning concepts and model evaluation techniques.

Nice to have

  • Databricks experience is highly preferred.
  • Experience with advanced agentic patterns, such as planner-executor, reflection, and memory-augmented agents.
  • Exposure to multimodal AI systems involving text, vision, or structured data fusion.
  • Familiarity with LLM evaluation techniques, including synthetic test generation and prompt regression testing.
  • Experience with advanced chunking strategies and context window optimization.
  • Exposure to LLMOps/MLOps practices for deployment, monitoring, and scaling AI systems.

Details

  • Location: Hyderabad Tech Center, Hyderabad, Telangana, India.
  • Hybrid working model: 3 days per week in the office and 2 days remote.
  • Candidates are expected to reside within a commuting distance of the Hyderabad office.
  • No travel required.
  • No visa sponsorship.
  • Domestic relocation applicable.
  • Employee status: Regular.

Read the full description and apply on the company’s own careers page.

Stay safe

Hiring on Abekus is free for applicants

We never charge a fee, and employers are prohibited from doing so. If a recruiter asks for payment, please report them right away.

Senior Specialist, AI Engineering