Nasiko is building the intelligent coordination layer for AI agents – a system that enables autonomous agents, data services, and infrastructure components to discover, register, and interact seamlessly. Our mission is to create an open, self-organizing AI ecosystem where agents can reason, collaborate, and transact without centralized control or human micromanagement. At the heart of this vision lies the Nasiko Registry: a shared substrate for observability, execution, and interoperability across distributed AI systems. We operate at the intersection of multi-agent intelligence, system orchestration, and adaptive infrastructure – building the primitives that make AI systems composable, transparent, and intelligent by design.

 

As a Senior Backend Developer at Nasiko, you will design, build, and optimize high-performance backend systems that power our distributed AI ecosystem. You will collaborate closely with ML engineers, platform teams, and infrastructure groups to deploy AI-powered services, scale intelligent workflows, and serve models efficiently across diverse environments. Your work will be central to Nasiko’s mission of enabling robust, interoperable, and adaptive AI coordination.

 

Develop and maintain backend systems, microservices, and APIs using Python.

Architect and deploy distributed infrastructure for high-throughput AI workloads.

Collaborate with ML engineers to integrate trained models into scalable production environments.

Build and maintain real-time and batch inference pipelines for AI-driven tasks.

Contribute to DevOps and MLOps workflows, including CI/CD automation, observability, monitoring, and autoscaling.

Ensure high availability, performance, and security across backend deployments.

Optimize internal tooling, model-serving infrastructure, and large-scale system performance.

 

Strong professional experience with Python in production-grade systems.

Deep understanding of distributed systems, Python asyncio models, and network programming.

Familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX.

Hands-on experience with model-serving platforms like Triton Inference Server, TorchServe, ONNX Runtime, or Ray Serve.

Proficiency in containerization (Docker) and orchestration (Kubernetes).

Experience with MLOps tools such as MLflow, Weights & Biases, Kubeflow, or Airflow.

Strong grasp of cloud platforms (AWS, GCP, Azure) and infrastructure-as-code.

Experience with SQL/NoSQL databases, caching systems (Redis), and message queues (Kafka, RabbitMQ).

Proficiency in Git and modern GitHub/GitLab workflows.

Bachelor’s degree in Computer Science, Engineering, or related fields is a plus.

 

Experience working with LLMs or foundation model architectures.

Familiarity with vector databases such as FAISS, Pinecone, or Weaviate.

Exposure to LLM orchestration frameworks (LangChain, LlamaIndex, Haystack).

Experience with graph processing, streaming systems, or real-time inference platforms.

Interest in AI evaluation, interpretability, or safety methodologies.

 

Build state-of-the-art infrastructure powering applied AI at scale.

Collaborate with a world-class team of engineers, scientists, and researchers.

Contribute to open-source tooling and research-driven development.

Competitive compensation with a dynamic, in-office culture in Bangalore.