About The Company
Tecinvent Software Pvt Ltd is a leading technology firm specializing in innovative software solutions and cutting-edge AI applications. Committed to driving digital transformation, Tecinvent leverages the latest advancements in artificial intelligence, machine learning, and cloud computing to deliver scalable, reliable, and impactful products for clients across various industries. Our collaborative and dynamic work environment fosters creativity, continuous learning, and professional growth, making Tecinvent a preferred employer for talented engineers and technologists seeking to make a difference in the tech landscape.
About The Role
We are seeking passionate and skilled Junior and Senior AI Engineers to join our innovative team at Tecinvent. In this role, you will be instrumental in designing, developing, and deploying production-grade Generative AI applications at medium to large scale. Your responsibilities will encompass end-to-end AI system development—from selecting appropriate models and frameworks to ensuring robust deployment, ongoing monitoring, and continuous enhancement of AI solutions. You will operate with minimal supervision, mentor junior engineers, and collaborate closely with cross-functional teams including Product, Design, Data, and Platform to deliver solutions that generate measurable business impact.
This is an exciting opportunity for engineers who are eager to work on state-of-the-art AI projects, particularly in the realm of generative models, agentic systems, and retrieval-augmented generation (RAG). Your expertise will directly influence the development of intelligent automation tools, content management systems, and workflow automation solutions that redefine industry standards.
Responsibilities
- Build and ship Generative AI applications: Develop, deploy, and maintain scalable, production-grade systems leveraging GenAI technologies, including retrieval-augmented generation, intelligent agents, copilots, and content automation tools.
- Design and implement agentic workflows: Architect complex, reliable agent-based systems that utilize tool use, function calling, planning, memory, and reflection to automate intricate tasks with safety and efficiency.
- Own architecture and scalability: Create secure, cost-efficient, and high-performance architectures capable of supporting both batch and real-time processing, with an emphasis on latency optimization and throughput planning.
- Model and tooling expertise: Select, fine-tune, and integrate large language models (LLMs) and GenAI tools, including embeddings, rerankers, multimodal models, and prompt/agent frameworks to meet project requirements.
- Evaluation and quality assurance: Develop comprehensive evaluation frameworks to measure accuracy, relevancy, safety, and hallucination reduction, implementing offline and online testing strategies, including A/B experiments.
- Data and retrieval systems: Design effective retrieval strategies, build indexing pipelines, optimize chunking, manage metadata, and utilize vector databases/search systems along with caching mechanisms for efficient data access.
- LLMOps / MLOps: Implement CI/CD pipelines, manage models and versions, automate testing, monitoring, alerting, and establish rollback procedures to ensure system stability and compliance.
- Security and governance: Apply best practices for data privacy, PII handling, access controls, audit logging, content filtering, and policy adherence to maintain system integrity and compliance.
- Mentorship and leadership: Guide junior engineers through code reviews, technical discussions, and best practices. Establish standards and patterns for AI engineering excellence within the team.
- Cross-team collaboration: Partner effectively with Product, Design, Data, and Platform teams to define project requirements, set milestones, and measure success metrics, ensuring alignment with business goals.
Qualifications
- 3+ years of experience in software engineering with a focus on ML/AI systems, including significant hands-on work in Generative AI at medium to large scale.
- Proven track record of delivering reliable, high-performance, production-grade GenAI applications with strong observability and cost management.
- Expertise in building and deploying agentic systems, including tool integration, orchestration, and failure handling in production environments.
- Strong programming skills in Python, with additional proficiency in TypeScript, Java, or Go considered a plus. Ability to write clean, maintainable, and well-tested code.
- Deep understanding of LLMs, prompt engineering, structured output generation, and tool integration.
- Experience with RAG pipelines, embeddings, reranking, retrieval optimization, and vector search technologies.
- Hands-on experience with distributed systems, REST/gRPC APIs, asynchronous processing, queues, caching, and rate limiting mechanisms.
- Familiarity with cloud platforms such as AWS, GCP, or Azure, and containerization tools like Docker and Kubernetes.
- Knowledge of monitoring and evaluation techniques for GenAI systems, including safety, quality metrics, drift detection, latency, and cost analysis.
- Ability to work independently, take ownership of projects, and drive initiatives forward with minimal oversight.
- Experience mentoring junior engineers and collaborating effectively across multidisciplinary teams.
Qualifications
- Experience in fine-tuning and adapting models using techniques like LoRA or PEFT, especially for multi-modal use cases.
- Familiarity with common GenAI stacks, including orchestration frameworks, vector databases, observability tools, feature flags, and experimentation platforms.
- Understanding of security and privacy by design principles, including compliance with standards such as SOC2, HIPAA, and handling of PII data.
- Proven ability to lead technical roadmaps and influence architecture decisions across teams to align with organizational goals.
