AI Engineer- Enterprise Platform Engineering

About Company :

GSPANN is a global IT services and consultancy provider headquartered in Milpitas, California (U.S.A.). With five global delivery centers across the globe, GSPANN provides digital solutions that support the customer buying journeys of B2B and B2C brands worldwide.

With a strong focus on innovation and client satisfaction, GSPANN delivers cutting-edge solutions that drive business success and operational excellence. GSPANN helps retail, finance, manufacturing, and high-technology brands deliver competitive customer experiences and increased revenues through our solution delivery, technologies, practices, and operations for each client. For more information, visit www.gspann.com

Position: AI Engineer, Enterprise Platform Engineering

Experience: 8+ years

Location: Hyderabad

Employment Type: Full-Time

About this team

The AI Engineering team builds secure, reliable, and observable AI-enabled systems that help engineering teams understand code, automate repetitive work, and make better decisions. You will work with developers, security teams, researchers, and platform partners to turn emerging AI capabilities into production-grade tools that improve software quality across repositories, languages, and teams .

What you’ll do

As an AI Engineer, you will design and operate an AI-driven code review platform. You will combine model reasoning, repository context, deterministic tools, and secure workflow infrastructure to produce accurate, actionable findings while managing reliability, latency, and cost.

• Design, build, and maintain an AI-driven code review system that helps agents understand code changes, investigate repository context, and produce actionable findings.
• Develop agent execution loops that coordinate model responses, code search, static analysis, and test execution to identify bugs, security vulnerabilities, and engineering standards violations.
• Build secure execution environments and workflow infrastructure for reviews, including sandboxing, access controls, state management, retries, and integration with pull requests and CI/CD pipelines.
• Create evaluation datasets and debugging tools that measure review quality, detect regressions, and distinguish model errors from context retrieval, tool execution, and orchestration failures.
• Run controlled experiments across models, prompts, context selection, and review strategies to improve issue detection, reduce false positives, and manage latency and cost.
• Own production reliability and observability, including review traces, model usage, failure diagnostics, and incident response.
• Work with developers, security teams, and researchers to turn engineering standards and reviewer feedback into measurable improvements in review accuracy and usefulness.
• Build shared tools and integrations that make automated reviews easier to extend and maintain across repositories, languages, and teams.

Qualifications

• Bachelor’s degree or diploma in Computer Science, Software Engineering, Machine Learning, or a related field preferred; equivalent relevant industry experience is also accepted.
• 6–8 years of software engineering experience, including hands-on work with AI-enabled or developer-tooling systems.

Important skills

• Comfortable using emerging technologies such as Codex, ChatGPT, and the OpenAI API to script or engineer Python solutions that automate repetitive tasks and integrate tools.
• Expert-level SaaS troubleshooting skills, with the ability to rapidly understand new technologies and complex concepts.
• Strong Python engineering skills and experience building production services, APIs, and automation.
• Experience integrating large language models through APIs and designing prompts, tool calls, context selection, and structured outputs.
• Experience with code search, repository analysis, static analysis, test automation, or developer productivity platforms.
• Understanding of agent orchestration, retrieval workflows, state management, retries, and failure recovery.
• Experience building evaluation datasets, quality metrics, regression tests, and debugging tools for AI systems.
• Knowledge of secure software design, sandboxing, access controls, secrets handling, and vulnerability detection.
• Strong observability and production troubleshooting skills across traces, logs, metrics, model usage, and distributed workflows.
• Strong written and verbal communication skills, with experience wor…