CLOUDSUFI

About Us :

CLOUDSUFI, a Google Cloud Premier Partner, a Data Science and Product Engineering organization building Products and Solutions for Technology and Enterprise industries. We firmly believe in the power of data to transform businesses and make better decisions. We combine unmatched experience in business processes with cutting edge infrastructure and cloud services. We partner with our customers to monetize their data and make enterprise data dance.

Our Values :

We are a passionate and empathetic team that prioritizes human values. Our purpose is to elevate the quality of lives for our family, customers, partners and the community.

Equal Opportunity Statement :

CLOUDSUFI is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified candidates receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, and national origin status. We provide equal opportunities in employment, advancement, and all other areas of our workplace.

Role : Architect/Lead-Python(Hands-on experience with at least one SaaS ingestion platform such as Fivetran ,Airbyte,etc. is mandatory.)

Location : Noida, Delhi/NCR(Hybrid)

Experience : 8- 14 years

Education : BTech / BE / MCA / MSc Computer Science

Must have :

- 6+ years of data engineering; at least 3 years working on connector or integration framework development

- Deep Python expertise including PySpark, pyarrow, and an understanding of Spark's execution model (driver vs executor, serialization constraints, partition fan-out)

- Hands-on experience with at least one SaaS ingestion platform Fivetran, Airbyte, Google DTS, AWS Glue connectors, or equivalent at the connector-build level, not just configuration

- Strong understanding of OAuth 2.0 flows (auth code, PKCE, client credentials, JWT), rate limiting strategies (token bucket, leaky bucket, per-endpoint quotas), and incremental sync patterns (cursor, watermark, CDC)

- Experience designing shared connector frameworks reusable auth managers, rate governors, state stores not just per-connector scripts

- Ability to author and own TDDs and PRDs that can be handed to a junior engineer with minimal back-and-forth

Nice to have :

- Prior exposure to Databricks Asset Bundles / Declarative Automation Bundles or Lakeflow pipelines

- Experience with the Databricks Python Data Source API (DBR 15.4 LTS+) extremely rare, so treat practical Spark DSv2 Java/Scala background as equivalent

- GCP DTS or Cloud Data Fusion connector experience

- Knowledge of the specific source systems, particularly Social Ads APIs (Meta, LinkedIn, X) or enterprise SaaS (Salesforce, Oracle)

About Us :

CLOUDSUFI, a Google Cloud Premier Partner, a Data Science and Product Engineering organization building Products and Solutions for Technology and Enterprise industries. We firmly believe in the power of data to transform businesses and make better decisions. We combine unmatched experience in business processes with cutting edge infrastructure and cloud services. We partner with our customers to monetize their data and make enterprise data dance.

Our Values :

We are a passionate and empathetic team that prioritizes human values. Our purpose is to elevate the quality of lives for our family, customers, partners and the community.

Equal Opportunity Statement :

CLOUDSUFI is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified candidates receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, and national origin status. We provide equal opportunities in employment, advancement, and all other areas of our workplace.

Role : Lead AI/Senior Engineer-AI

Location : Noida, Delhi/NCR

Experience : 5- 12 years

Education : BTech / BE / MCA / MSc Computer Science

Must Haves :

Conversational AI & NLU :

- Advanced proficiency with Dialogflow CX

- Intent classification, entity extraction, conversation flow design

- Experience building structured dialogue flows with routing logic CCAI platform familiarity

Agentic AI & Multi-Step Reasoning :

- Production experience with Google ADK (or LangChain/LangGraph equivalent)

- Multi-step reasoning and tool orchestration capability

- Tool-use patterns and function calling implementation

RAG Systems & Knowledge Management :

- Hands-on Vertex AI RAG Engine experience (or equivalent)

- Semantic search, chunking strategies, retrieval optimization

- Document processing pipelines (PDF parsing, chunking)

LLM/GenAI & Prompt Engineering :

- Production experience with Gemini models

- Advanced prompt engineering for customer support

- Langfuse experience for prompt management

Google Cloud Platform & Vertex AI :

- Advanced Vertex AI proficiency (Generative AI APIs, Agent Engine)

- Cloud Functions and Cloud Run deployment experience

- BigQuery for conversation analytics

API Integration :

- Genesys Cloud CX integration experience

- REST API design and webhook implementation

- Enterprise authentication patterns (OAuth 2.0)

Good To Have :

Conversational AI & NLU :

- Multi-language support implementation (Spanish/English)

- Telephony integration (speech recognition, TTS, DTMF)

- Barge-in handling and voice optimization

Agentic AI :

- Agent state management and session persistence

- Advanced fallback strategies and error recovery

- Dynamic tool selection and evaluation

RAG Systems :

- Re-ranking and advanced retrieval quality metrics

- Query expansion and context-aware retrieval

- Corpus organization strategies

LLM/GenAI :

- Prompt versioning, A/B testing, iterative refinement

- Prompt injection mitigation strategies

- In-context learning, few-shot, chain-of-thought techniques

LLMOps & Observability :

- Vertex AI Evaluation Service experience

- Groundedness, relevance, coherence, safety metrics

- Trace-level debugging with Cloud Trace

- Centralized logging strategies

Google Cloud :

- Application Integration connectors

- VPC Service Controls and enterprise security

- Cloud Pub/Sub for event-driven systems

Enterprise Integration :

- Third-party AI agent orchestration (SAP Joule, ServiceNow AI, Agentforce)

- Salesforce, SAP, ServiceNow integration patterns

- Context passage strategies for escalations

Architecture & System Design :

- Configuration-driven systems (Meta-Agent patterns)

- Microservices and containerization

- Scalable, multi-tenant system design

- Disaster recovery and failover strategies

Product Quality & KPIs :

- Customer support metrics expertise (CSAT, SSR, escalation rate)

- A/B testing and experimentation frameworks

- User feedback loop implementation

Deliverables :

- Architecture Design : End-to-end platform architecture, data flow diagrams, Dialogflow CX vs. ADK routing decisions

- Conversational Flows : 15+ dialogue flows covering billing, networking, appointments, troubleshooting, and escalations

- ADK Agent Implementation : Complex reasoning agents for technical support, account analysis, and context preparation

- RAG Pipeline : Document processing, chunking configuration, corpus organization (product docs, support articles, policies, promotions)

- Prompt Management : System prompts, Langfuse setup, playbook governance, version control

- Quality Framework : Evaluation pipeline, metrics dashboards, automated assessment, continuous improvement recommendations

- Integration Layer : Genesys handoff, webhook integrations, Application Integration setup, session management

- Testing & Validation : Conversation flow tests, performance testing (latency, throughput, 1000 concurrent users), security validation

- Response time <2 seconds (p95), 99.9% uptime, 1000 concurrent conversations

- Data encryption (TLS 1.2+, AES-256 at rest), PII redaction, 1-year data retention

- Graceful degradation and fallback mechanisms

We at CLOUDSUFI are hiring for Workato AI Integration Consultants.

Location - Remote

Type - Contractual (6months and extendable)

Shift - 3pm-12am

Qualifications:

• Bachelor's degree in Computer Science, Information Technology, Engineering, or a related field, or equivalent practical experience.

• Proven 5+ years of hands-on experience in designing, developing, and deploying integrations using the Workato platform.

• Strong understanding of Integration Platform as a Service (iPaaS) concepts and enterprise application integration (EAI) patterns.

• Demonstrated experience with Workato's AI capabilities, including building solutions with AI by Workato, IDP, or Agentic AI.

• Proficiency in working with various APIs (REST, SOAP), webhooks, and different data formats (JSON, XML, CSV).

• Experience with scripting languages (e.g., Ruby, Python, JavaScript) for custom logic within Workato recipes is a plus.

• Solid understanding of database concepts and experience with SQL/NoSQL databases.

• Excellent problem-solving, analytical, and troubleshooting skills with keen attention to detail.

• Strong communication and interpersonal skills, with the ability to effectively collaborate with technical and non-technical stakeholders.

• Workato certifications (e.g., Automation Pro I, II, III, Integration Developer) are desirable.

• Experience with Agile/Scrum methodologies is a plus.

Preferred Skills (Nice to Have):

• Experience with other integration platforms (e.g., MuleSoft, Boomi, Zapier).

• Familiarity with cloud platforms (AWS, Azure, GCP).

• Knowledge of microservices architecture.

• Experience with version control systems (e.g., Git).

Highlights - Current location of candidate should be Bangalore

Total Exp - 6-12yrs

Joining Time period - Within 30 days

GCP Bigquery expert, GCP Certified

About Us

CLOUDSUFI, a Google Cloud Premier Partner, is a global leading provider of data-driven digital transformation across cloud-based enterprises. With a global presence and focus on Software & Platforms, Life sciences and Healthcare, Retail, CPG, financial services and supply chain, CLOUDSUFI is positioned to meet customers where they are in their data monetization journey.

Our Values 

We are a passionate and empathetic team that prioritizes human values. Our purpose is to elevate the quality of lives for our family, customers, partners and the community.

Equal Opportunity Statement 

CLOUDSUFI is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified candidates receive consideration for employment without regard to race, colour, religion, gender, gender identity or expression, sexual orientation and national origin status. We provide equal opportunities in employment, advancement, and all other areas of our workplace. Please explore more at https://www.cloudsufi.com/

Job Summary

We are seeking a highly skilled and motivated Data Engineer to join our Development POD for the Integration Project. The ideal candidate will be responsible for designing, building, and maintaining robust data pipelines to ingest, clean, transform, and integrate diverse public datasets into our knowledge graph. This role requires a strong understanding of Cloud Platform (GCP) services, data engineering best practices, and a commitment to data quality and scalability.

Key Responsibilities

ETL Development: Design, develop, and optimize data ingestion, cleaning, and transformation pipelines for various data sources (e.g., CSV, API, XLS, JSON, SDMX) using Cloud Platform services (Cloud Run, Dataflow) and Python.

Schema Mapping & Modeling: Work with LLM-based auto-schematization tools to map source data to our schema.org vocabulary, defining appropriate Statistical Variables (SVs) and generating MCF/TMCF files.

Entity Resolution & ID Generation: Implement processes for accurately matching new entities with existing IDs or generating unique, standardized IDs for new entities.

Knowledge Graph Integration: Integrate transformed data into the Knowledge Graph, ensuring proper versioning and adherence to existing standards. 

API Development: Develop and enhance REST and SPARQL APIs via Apigee to enable efficient access to integrated data for internal and external stakeholders.

Data Validation & Quality Assurance: Implement comprehensive data validation and quality checks (statistical, schema, anomaly detection) to ensure data integrity, accuracy, and freshness. Troubleshoot and resolve data import errors.

Automation & Optimization: Collaborate with the Automation POD to leverage and integrate intelligent assets for data identification, profiling, cleaning, schema mapping, and validation, aiming for significant reduction in manual effort.

Collaboration: Work closely with cross-functional teams, including Managed Service POD, Automation POD, and relevant stakeholders.

Qualifications and Skills

Education: Bachelor's or Master's degree in Computer Science, Data Engineering, Information Technology, or a related quantitative field.

Experience: 6+ years of proven experience as a Data Engineer, with a strong portfolio of successfully implemented data pipelines.

Programming Languages: Proficiency in Python for data manipulation, scripting, and pipeline development.

Cloud Platforms and Tools: Expertise in Google Cloud Platform (GCP) services, including Cloud Storage, Cloud SQL, Cloud Run, Dataflow, Pub/Sub, BigQuery, and Apigee. Proficiency with Git-based version control.

Core Competencies:

Must Have - SQL, Python, BigQuery, (GCP DataFlow / Apache Beam), Google Cloud Storage (GCS)

Must Have - GCP Certification

Must Have - Proven ability in comprehensive data wrangling, cleaning, and transforming complex datasets from various formats (e.g., API, CSV, XLS, JSON)

Secondary Skills - SPARQL, Schema.org, Apigee, CI/CD (Cloud Build), GCP, Cloud Data Fusion, Data Modelling

Solid understanding of data modeling, schema design, and knowledge graph concepts (e.g., Schema.org, RDF, SPARQL, JSON-LD).

Experience with data validation techniques and tools.

Familiarity with CI/CD practices and the ability to work in an Agile framework.

Strong problem-solving skills and keen attention to detail.