AI Engineer

We are looking for an AI Engineer to help design, build, and operationalise AI-powered capabilities that make Recast's products smarter, more scalable, and easier for customers to use. This role will work closely with product, engineering, data, and cloud teams to integrate large language models, agentic AI patterns, vector databases, APIs, data pipelines, AI evaluation harnesses, and usage monitoring into reliable production systems. The ideal candidate is a hands-on engineer who can move from prototype to production, write high-quality software, measure AI quality and adoption, and apply strong engineering practices across cloud, data, and AI workloads. This is a hybrid position that will work out of our office in Manayata Tech Park, Bangalore, India.

Responsibilities:

• Build and integrate production-ready AI features using Python, LLM APIs, vector databases, agentic AI patterns, and AI evaluation harnesses.
• Apply strong software engineering practices, including Git-based development, CI/CD, containers, API development, and reliable deployment workflows.
• Design and maintain data and cloud foundations for AI workloads, including SQL databases, data pipelines, messaging patterns, and cloud services across platforms such as AWS and Azure.
• Develop, test, and deploy AI-enabled product features and services using modern software engineering practices.
• Integrate large language model APIs into product workflows, including prompt orchestration, response handling, evaluation and reliability considerations.
• Create and maintain AI evaluation harnesses to test prompt quality, retrieval accuracy, response consistency, safety guardrails, regression behaviour, and overall feature reliability.
• Design and implement an agentic framework with audit, traceability and guardrails.
• Build and maintain APIs, services, and data pipelines that support AI use cases, including SQL-based data access and pipeline tools such as Apache Airflow or Spark.
• Collaborate with product managers, designers, engineers, and stakeholders to translate business needs into practical AI solutions.
• Contribute to technical design discussions, documentation, code reviews, operational readiness, and continuous improvement of AI engineering practices.
• Build and deploy ML models that can troubleshoot compliance-related issues for customers.
• Design and implement retrieval-augmented generation and semantic search patterns using vector databases and relevant data stores.

Requirements:

• One year of AI Engineering experience.
• 5+ years of professional software engineering experience building production-quality services or applications.
• Hands-on experience integrating LLM APIs and applying agentic AI concepts, including tool use, workflow orchestration, multi-step reasoning patterns, autonomous task execution, and AI evaluation approaches.
• Experience creating AI evaluation harnesses, test datasets, metrics, or monitoring workflows to assess quality, reliability, usage, cost, latency, and production behaviour of AI features.
• Practical experience with vector databases, SQL databases, API development, and data pipeline technologies such as Apache Airflow, Spark, or comparable tools.
• Strong software engineering fundamentals, including Git version control, CI/CD, containers, testing practices, and maintainable code design.
• Experience deploying or supporting workloads on cloud platforms such as AWS, Azure, or similar cloud environments.
• Hands-on experience with Git, CI/CD, containers, and deployment automation to deliver secure, observable, and maintainable software.

Preferred Knowledge and Skills:

• Knowledge of prompt engineering techniques, model evaluation approaches, and practical tradeoffs when building AI-enabled user experiences.
• Domain knowledge in endpoint management, IT operations, security, compliance, enterprise software, or related product areas.
• Familiarity with infrastructure as code, cloud cost considerations for AI deployments, and secure development practices.
• Ability to write clear technical documentation, design notes, runbooks, or implementation guides for engineering and cross-functional audiences.
• Hands-on experience using notebooks such as Jupyter or Google Colab for experimentation, prototyping, analysis, or demos.
• Curiosity, enthusiasm to learn, and willingness to explore emerging AI tools, frameworks, and engineering patterns.