Company: Farmioc
Location: Pune, Maharashtra, India
Work Model: On-site
Employment Type: Full-time
Experience: 3–5 Years

Farmioc is an Agri Intelligence & Commodity Trading Ecosystem focused on helping businesses and stakeholders across the agriculture and food value chain make better, data-driven decisions.

Its products include DataStore, PriceHub, MarketHub, AgriTools, and AGVISOR, covering agricultural data, market intelligence, commodity trading, analytics, and decision-support use cases.

We are looking for an AI Platform Engineer to build and maintain the infrastructure and platform capabilities that support Farmioc's AI-enabled, data, and software applications.

You will work across cloud infrastructure, AI service integrations, deployment automation, LLM observability, cost management, CI/CD, and production reliability.

The role is particularly focused on making AI applications reliable and practical to operate in production. This includes managing how applications connect to AI providers, monitoring AI usage and costs, improving deployment workflows, and building the infrastructure required to run AI-enabled features across Farmioc products.

• Build reusable platform components for Farmioc's AI-enabled applications.

• Develop common patterns for integrating LLM and AI services into production applications.

• Build or maintain an AI gateway layer for provider configuration, API access, retries, rate limits, and fallback handling where required.

• Implement usage and cost tracking for AI services across products and features.

• Monitor LLM request latency, failures, usage, and service availability.

• Support secure handling of prompts, application data, API credentials, and AI-provider integrations.

• Work with engineering teams to improve the reliability and operational efficiency of AI workloads.

• Build and maintain cloud infrastructure supporting Farmioc's AI, data, and application workloads.

• Work with AWS and other relevant cloud services for compute, storage, networking, databases, and application deployment.

• Build and maintain CI/CD pipelines for backend, AI, and data applications.

• Containerize applications and services using Docker and support container orchestration where required.

• Automate environment configuration and deployments across development, staging, and production.

• Use Infrastructure as Code to make infrastructure changes repeatable and maintainable.

• Implement monitoring and tracing for AI applications, APIs, and supporting services.

• Track AI application metrics such as latency, failures, request volume, token usage, and cost.

• Support evaluation workflows for prompts, models, and AI application changes before production releases.

• Build logging, alerting, health checks, retries, and recovery mechanisms for AI services.

• Investigate production issues involving AI providers, APIs, infrastructure, and application dependencies.

• Improve reliability while balancing AI performance, quality, and operating cost.

• Manage secrets, service credentials, authentication, authorization, and access controls for platform services.

• Apply secure patterns when connecting Farmioc applications to external AI providers and cloud services.

• Help define appropriate controls for sending customer, agricultural, and market data to external AI services.

• Protect APIs, databases, AI services, and internal platform components.

• Support secure configuration and deployment across development and production environments.

• Build reusable deployment templates, scripts, tools, and workflows for engineering teams.

• Simplify local development, testing, deployment, and monitoring of AI-enabled applications.

• Provide standardized approaches for configuration, logging, observability, and production readiness.

• Troubleshoot infrastructure, deployment, API, database, and AI-service issues.

• Participate in production incident investigation and root-cause analysis.

• Identify repetitive infrastructure work and automate it where practical.

• 3–5 years of experience in platform engineering, cloud engineering, DevOps, infrastructure engineering, backend engineering, or a related field.

• Strong experience with AWS or another major cloud platform.

• Strong experience with Docker and production application deployment.

• Experience building and maintaining CI/CD pipelines.

• Strong scripting or programming skills in Python, Bash, or a similar language.

• Good understanding of Linux, networking, APIs, databases, and production systems.

• Experience with monitoring, logging, troubleshooting, and production operations.

• Understanding of authentication, authorization, secrets management, and infrastructure security.

• Experience working with external APIs and cloud services.

• Strong debugging and problem-solving skills.

• Experience supporting LLM or Generative AI applications in production.

• Experience working with LLM APIs such as OpenAI, Anthropic, Google, Azure OpenAI, or similar providers.

• Experience building AI gateways, provider integrations, usage tracking, or AI cost monitoring.

• Familiarity with LLM tracing, evaluation, prompt/version management, or AI observability.

• Experience with Kubernetes or other container orchestration platforms.

• Experience with Terraform or another Infrastructure-as-Code tool.

• Familiarity with Redis, PostgreSQL, MongoDB, message queues, or background processing systems.

• Experience with tools such as Prometheus, Grafana, OpenTelemetry, or similar observability platforms.

• Experience deploying production AI, data, or analytics applications.

• Familiarity with model serving or GPU infrastructure is a plus where applicable.

AI Platform Engineering | Cloud Engineering | AWS | Python | Docker | CI/CD | LLM APIs | Generative AI | AI Observability | AI Cost Optimization | Platform Engineering | Infrastructure as Code | APIs | Linux | Monitoring | Logging | Security | Production Engineering | PostgreSQL | Redis

• Build the platform capabilities behind real-world agricultural data, analytics, and AI applications.

• Work on practical AI infrastructure problems involving reliability, observability, cost, and production deployment.

• Help establish reusable patterns for integrating and operating AI services.

• Work across cloud, backend, data, and AI-enabled applications.

• Have ownership over platform improvements that directly support Farmioc's products.

Farmioc is committed to providing equal employment opportunities and maintaining an inclusive and professional workplace.