Position Summary The Senior AI Engineer is a highly experienced individual contributor responsible for solving complex, high-impact problems through the applied use of AI in production software systems.

This role goes beyond execution alone. The Senior AI Engineer will define how AI is built and used by setting implementation patterns, quality standards, and technical guardrails that can scale across engineering teams.

The role involves leading critical initiatives end to end, working effectively in ambiguous problem spaces, and making high-impact technical decisions involving models, agentic systems, architecture, and engineering trade-offs.

The ideal candidate will build and operate AI-enabled systems that meet enterprise expectations for reliability, performance, cost efficiency, security, and safety.

This is not a research or theoretical machine learning role. The focus is on applied, production-grade AI, including agentic systems, model-driven workflows, AI automation, and integration of AI capabilities into real-world software products.

Key Responsibilities

Advanced AI Engineering & System Design

- Design, build, and operate sophisticated AI-enabled software systems that solve complex business and product challenges.
- Architect and implement agentic systems capable of autonomous tool selection, multi-step goal execution, and controlled decision-making in production environments.
- Define and implement Model Context Protocol (MCP) patterns for managing tools, context, memory, policies, and system boundaries at scale.
- Make informed decisions on model selection, composition, and deployment by balancing reasoning quality, latency, cost, and reliability.
- Treat model behavior, agent flows, prompts, and contextual inputs as core system components that are designed, versioned, tested, and observable.
- Design scalable AI architectures and contribute to system and architecture design decisions for AI-powered applications.

Technical Leadership & Initiative Ownership

- Serve as a technical lead for high-impact AI initiatives, owning architecture, execution strategy, and delivery outcomes.
- Break down ambiguous and open-ended problems into clear technical approaches and guide implementation.
- Identify system-level risks, failure modes, and technical trade-offs early and address them through appropriate design and safeguards.
- Influence technical direction across teams through technical expertise, judgment, and strong engineering practices.
- Take ownership of the long-term technical health and scalability of AI-enabled systems.

AI-First Development Practices & Standards

- Define and evolve effective AI development practices across engineering teams, including:




- AI-assisted and AI-generated code
- Agent-based engineering workflows
- AI-driven testing, debugging, and refactoring
- AI-enabled documentation and observability
- Establish standards and best practices for:
- Agent behavior and autonomy
- Prompt and context design
- Model selection and usage
- AI evaluation and regression detection
- Safe and explainable AI behavior in production
- Promote AI as an integrated capability within engineering workflows rather than an experimental or standalone initiative.

Mentorship & Capability Building

- Mentor AI Engineers through technical guidance, design discussions, pairing, and code reviews.
- Improve AI engineering practices, system thinking, and technical rigor across teams.
- Share reusable patterns, lessons learned, and failure analyses.
- Act as a technical resource for complex AI, GenAI, and agentic system challenges.

Product & Cross-Functional Collaboration

- Partner closely with Product, Design, and Engineering teams to deliver AI-powered features end to end.
- Translate product requirements into scalable and maintainable technical architectures.
- Balance development speed, quality, security, safety, and maintainability when making technical decisions.
- Communicate complex AI and agentic system concepts clearly to both technical and non-technical stakeholders.
- Help product and engineering teams understand AI capabilities, limitations, and trade-offs.

Quality, Reliability & Accountability

- Ensure AI-enabled systems meet high standards for security, performance, reliability, and compliance.
- Design and implement evaluation, monitoring, and safeguard strategies for AI behavior in production.
- Address areas such as:
- Hallucination and error detection
- Traceability and explainability
- Behavioral regression and drift
- Model performance and reliability
- Cost and latency optimization
- Monitor and improve the operational stability, scalability, and cost efficiency of AI systems.

Continuous Improvement & Learning

- Stay current with AI tools, platforms, models, frameworks, and agentic patterns relevant to production systems.
- Evaluate emerging AI capabilities and responsibly incorporate proven approaches into engineering practices.
- Continuously improve how AI systems are designed, developed, evaluated,



and operated.
- Contribute to a culture of disciplined execution, continuous learning, and technical excellence.
- Perform other duties as assigned.

Required Qualifications

- Bachelor’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
- Extensive experience building and operating complex production software systems.
- Strong hands-on experience designing and operating Agentic AI systems in production, including autonomous tool usage and multi-step workflows.
- Robust technical expertise in Model Context Protocol (MCP) or equivalent approaches.
- Strong understanding of modern AI and foundation models, including:
- Model names, versions, and parameter scales
- Context window limitations and optimization strategies
- System prompts vs. user prompts
- Model selection and trade-offs
- Latency, cost, reasoning quality, and reliability considerations
- Experience working with both frontier and open-source models and making informed decisions between them.
- Proven experience scaling AI systems and addressing:
- Latency optimization
- Cost optimization
- Caching
- Parallelization
- Model selection
- System scalability
- Proven ability to take complex AI systems from prototype to production and maintain them over time.
- Strong system design and architecture skills with the ability to make technical decisions for scalable AI applications.
- Strong problem-solving skills and the ability to operate effectively in ambiguous environments.

Preferred Qualifications

- Experience defining engineering standards, patterns, or platforms adopted by multiple teams.
- Experience designing AI platform architectures or shared agentic frameworks.
- Experience with cloud-native, SaaS, or platform-oriented environments.
- Experience working with enterprise, regulated, or mission-critical systems.
- Experience with modern AI development tools and AI-assisted software engineering workflows.
- Strong understanding of observability, evaluation frameworks, and production monitoring for AI systems.

What We’re Looking For

We value engineers who see AI as a force multiplier rather than a novelty. The ideal Senior AI Engineer is a strong builder and technical leader who takes ownership of outcomes, designs systems that scale safely, and uses AI to improve both product capabilities and engineering effectiveness.

If you are excited about designing and operating production-grade agentic AI systems, solving complex engineering problems, and shaping how AI is built and used across teams, this role is an opportunity to make a significant technical impact.

📌 Senior AI Engineer (Ahmedabad)
🏢 ProductSquads
📍 Ahmedabad