Senior AI Engineer – Agentic, Generative AI

SPAR Solutions

Senior AI Engineer at SPAR Solutions providing technical leadership on Agentic and Generative AI solutions. Involvement in design, coding, and client engagement in a consulting environment.

Posted 7/20/2026full-timePune • 🇮🇳 IndiaSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in Architecting and Delivering Agentic AI Systems, with a strong focus on LLM Integration Strategy, Prompt Engineering, and Multi-Agent System Design. Proficient in Python and Data Analysis, applying statistical methods to generate actionable insights while leading technical teams in client-facing engagements.

Highest-signal resume keywords

Agentic AI System ArchitectureLLM Integration StrategyPrompt EngineeringPython ProficiencyTest-Driven Development

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringGenerative AIMulti-Agent System DesignStatistical AnalysisData ExplorationAPI DesignUnit TestingAgile MethodologyMCP IntegrationsSystem Design

Soft Skills

Exceptional CommunicationTechnical LeadershipClient EngagementMentoringAdaptability

Tools & Technologies

PythonNumpyPandasClaude CodeOpenAI CodexGitHub CopilotLangChainLangGraphAutoGenVisualization Libraries

Industry Keywords

Agentic WorkflowsData Quality AssessmentDesign PatternsSOLID PrinciplesStatistical EDATechnical ScopingClient Discovery SessionsAI Coding AgentsModel SelectionContext Management

Tech Stack

Tools & technologies

Distributed SystemsNumpyPandasPython

About the role

Key responsibilities & impact

Architect and deliver Agentic AI systems - multi-agent orchestration, tool use, memory, planning loops, and MCP integrations
Design RAG pipelines and agentic workflows tailored to client knowledge and data landscapes
Lead LLM integration strategy - model selection, prompt engineering, context management, and structured outputs across providers
Use AI coding agents (Claude Code, Codex, Copilot, or equivalent) as a primary development tool; direct and validate AI-generated output with precision
Provide technical leadership on engagements - own solution design, drive requirements gathering and analysis, and guide the team through delivery
Lead client discovery sessions, technical scoping, and solution presentations; translate ambiguous business problems into well-defined AI solutions
Conduct design reviews, enforce engineering standards, and mentor junior and mid-level engineers
Drive technology selection; establish reusable patterns and internal frameworks that improve delivery across the team
Apply statistical analysis and EDA to client data problems; generate charts, graphs, and visual summaries that communicate findings clearly to both technical and non-technical audiences
Contribute to data quality assessment, pipeline design, and insight delivery using Python, numpy, and pandas
Write clean, testable code following SOLID principles and design patterns; apply test-driven development practices and write unit tests as a standard part of delivery
Stay current on the Agentic AI landscape and bring relevant advances into SPAR's delivery practice
Contribute to internal knowledge assets, accelerators, and capability building

Requirements

What you’ll need

10+ years in software engineering with at least 1 year focused on Generative and Agentic AI
Hands-on experience with at least one agentic framework - LangChain, LangGraph, AutoGen, CrewAI, or equivalent
Direct experience prompting and integrating major LLMs - OpenAI, Anthropic Claude, Google Gemini, or similar
Hands-on use of AI coding agents - Claude Code, OpenAI Codex, GitHub Copilot, or equivalent
Experience with MCP integrations, agentic workflows, and multi-agent system design
Strong prompt engineering skills - systematic, structured, and testable prompting practices
Foundational understanding of ML concepts - how models are trained, data preparation, purpose and mechanics of fine-tuning, and when to apply pre-trained vs. fine-tuned models
System design proficiency - distributed systems thinking, API design, scalability and reliability patterns
Applied statistics and EDA - comfortable with data exploration, distributions, correlation, and translating findings into actionable insights
Proficiency with Python, numpy, and pandas; experience with visualization libraries (matplotlib, seaborn, Plotly, or equivalent)
Test-driven development practices and unit testing experience
Experience leading technical workstreams or teams on client-facing consulting engagements
Exceptional communication - equally effective whether writing a precise technical spec or presenting to a non-technical audience
Agile methodology experience; comfortable owning delivery timelines and managing technical risk
High adaptability - thrives across client domains and technology stacks; fast, self-directed learner

Benefits

Comp & perks

Direct exposure to high-impact enterprise problems across industries
Hands-on technical role with real leadership influence - you design, build, and set direction
A fast-moving team where intellectual rigor and ownership are valued over hierarchy
Opportunity to shape SPAR's AI practice - the frameworks and standards you establish become the team's foundation